Merge tag 'xfs-6.12-fixes-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs fixes from Carlos Maiolino:

 - A few small typo fixes

 - fstests xfs/538 DEBUG-only fix

 - Performance fix on blockgc on COW'ed files, by skipping trims on
   cowblock inodes currently opened for write

 - Prevent cowblocks to be freed under dirty pagecache during unshare

 - Update MAINTAINERS file to quote the new maintainer

* tag 'xfs-6.12-fixes-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: fix a typo
  xfs: don't free cowblocks from under dirty pagecache on unshare
  xfs: skip background cowblock trims on inodes open for write
  xfs: support lowmode allocations in xfs_bmap_exact_minlen_extent_alloc
  xfs: call xfs_bmap_exact_minlen_extent_alloc from xfs_bmap_btalloc
  xfs: don't ifdef around the exact minlen allocations
  xfs: fold xfs_bmap_alloc_userdata into xfs_bmapi_allocate
  xfs: distinguish extra split from real ENOSPC from xfs_attr_node_try_addname
  xfs: distinguish extra split from real ENOSPC from xfs_attr3_leaf_split
  xfs: return bool from xfs_attr3_leaf_add
  xfs: merge xfs_attr_leaf_try_add into xfs_attr_leaf_addname
  xfs: Use try_cmpxchg() in xlog_cil_insert_pcp_aggregate()
  xfs: scrub: convert comma to semicolon
  xfs: Remove empty declartion in header file
  MAINTAINERS: add Carlos Maiolino as XFS release manager

MAINTAINERS

@@ -25404,7 +25404,7 @@ F:	include/xen/arm/swiotlb-xen.h
 F:	include/xen/swiotlb-xen.h
 
 XFS FILESYSTEM
-M:	Chandan Babu R <chandan.babu@oracle.com>
+M:	Carlos Maiolino <cem@kernel.org>
 R:	Darrick J. Wong <djwong@kernel.org>
 L:	linux-xfs@vger.kernel.org
 S:	Supported

fs/xfs/libxfs/xfs_alloc.c

@@ -2766,7 +2766,6 @@ xfs_alloc_commit_autoreap(
 		xfs_defer_item_unpause(tp, aarp->dfp);
 }
 
-#ifdef DEBUG
 /*
  * Check if an AGF has a free extent record whose length is equal to
  * args->minlen.
@@ -2806,7 +2805,6 @@ xfs_exact_minlen_extent_available(
 
 	return error;
 }
-#endif
 
 /*
  * Decide whether to use this allocation group for this allocation.
@@ -2880,15 +2878,14 @@ xfs_alloc_fix_freelist(
 	if (!xfs_alloc_space_available(args, need, alloc_flags))
 		goto out_agbp_relse;
 
-#ifdef DEBUG
-	if (args->alloc_minlen_only) {
+	if (IS_ENABLED(CONFIG_XFS_DEBUG) && args->alloc_minlen_only) {
 		int stat;
 
 		error = xfs_exact_minlen_extent_available(args, agbp, &stat);
 		if (error || !stat)
 			goto out_agbp_relse;
 	}
-#endif
+
 	/*
 	 * Make the freelist shorter if it's too long.
 	 *

fs/xfs/libxfs/xfs_alloc.h

@@ -53,11 +53,9 @@ typedef struct xfs_alloc_arg {
 	int		datatype;	/* mask defining data type treatment */
 	char		wasdel;		/* set if allocation was prev delayed */
 	char		wasfromfl;	/* set if allocation is from freelist */
+	bool		alloc_minlen_only; /* allocate exact minlen extent */
 	struct xfs_owner_info	oinfo;	/* owner of blocks being allocated */
 	enum xfs_ag_resv_type	resv;	/* block reservation to use */
-#ifdef DEBUG
-	bool		alloc_minlen_only; /* allocate exact minlen extent */
-#endif
 } xfs_alloc_arg_t;
 
 /*

fs/xfs/libxfs/xfs_attr.c

@@ -51,7 +51,6 @@ STATIC int xfs_attr_shortform_addname(xfs_da_args_t *args);
 STATIC int xfs_attr_leaf_get(xfs_da_args_t *args);
 STATIC int xfs_attr_leaf_removename(xfs_da_args_t *args);
 STATIC int xfs_attr_leaf_hasname(struct xfs_da_args *args, struct xfs_buf **bp);
-STATIC int xfs_attr_leaf_try_add(struct xfs_da_args *args);
 
 /*
  * Internal routines when attribute list is more than one block.
@@ -437,6 +436,33 @@ xfs_attr_hashval(
 	return xfs_attr_hashname(name, namelen);
 }
 
+/* Save the current remote block info and clear the current pointers. */
+static void
+xfs_attr_save_rmt_blk(
+	struct xfs_da_args	*args)
+{
+	args->blkno2 = args->blkno;
+	args->index2 = args->index;
+	args->rmtblkno2 = args->rmtblkno;
+	args->rmtblkcnt2 = args->rmtblkcnt;
+	args->rmtvaluelen2 = args->rmtvaluelen;
+	args->rmtblkno = 0;
+	args->rmtblkcnt = 0;
+	args->rmtvaluelen = 0;
+}
+
+/* Set stored info about a remote block */
+static void
+xfs_attr_restore_rmt_blk(
+	struct xfs_da_args	*args)
+{
+	args->blkno = args->blkno2;
+	args->index = args->index2;
+	args->rmtblkno = args->rmtblkno2;
+	args->rmtblkcnt = args->rmtblkcnt2;
+	args->rmtvaluelen = args->rmtvaluelen2;
+}
+
 /*
  * PPTR_REPLACE operations require the caller to set the old and new names and
  * values explicitly.  Update the canonical fields to the new name and value
@@ -482,48 +508,73 @@ xfs_attr_complete_op(
 	return replace_state;
 }
 
+/*
+ * Try to add an attribute to an inode in leaf form.
+ */
 static int
 xfs_attr_leaf_addname(
 	struct xfs_attr_intent	*attr)
 {
 	struct xfs_da_args	*args = attr->xattri_da_args;
+	struct xfs_buf		*bp;
 	int			error;
 
 	ASSERT(xfs_attr_is_leaf(args->dp));
 
+	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp);
+	if (error)
+		return error;
+
 	/*
-	 * Use the leaf buffer we may already hold locked as a result of
-	 * a sf-to-leaf conversion.
+	 * Look up the xattr name to set the insertion point for the new xattr.
 	 */
-	error = xfs_attr_leaf_try_add(args);
-
-	if (error == -ENOSPC) {
-		error = xfs_attr3_leaf_to_node(args);
-		if (error)
-			return error;
+	error = xfs_attr3_leaf_lookup_int(bp, args);
+	switch (error) {
+	case -ENOATTR:
+		if (args->op_flags & XFS_DA_OP_REPLACE)
+			goto out_brelse;
+		break;
+	case -EEXIST:
+		if (!(args->op_flags & XFS_DA_OP_REPLACE))
+			goto out_brelse;
 
+		trace_xfs_attr_leaf_replace(args);
 		/*
-		 * We're not in leaf format anymore, so roll the transaction and
-		 * retry the add to the newly allocated node block.
+		 * Save the existing remote attr state so that the current
+		 * values reflect the state of the new attribute we are about to
+		 * add, not the attribute we just found and will remove later.
 		 */
-		attr->xattri_dela_state = XFS_DAS_NODE_ADD;
-		goto out;
+		xfs_attr_save_rmt_blk(args);
+		break;
+	case 0:
+		break;
+	default:
+		goto out_brelse;
 	}
-	if (error)
-		return error;
 
 	/*
 	 * We need to commit and roll if we need to allocate remote xattr blocks
 	 * or perform more xattr manipulations. Otherwise there is nothing more
 	 * to do and we can return success.
 	 */
-	if (args->rmtblkno)
+	if (!xfs_attr3_leaf_add(bp, args)) {
+		error = xfs_attr3_leaf_to_node(args);
+		if (error)
+			return error;
+
+		attr->xattri_dela_state = XFS_DAS_NODE_ADD;
+	} else if (args->rmtblkno) {
 		attr->xattri_dela_state = XFS_DAS_LEAF_SET_RMT;
-	else
-		attr->xattri_dela_state = xfs_attr_complete_op(attr,
-							XFS_DAS_LEAF_REPLACE);
-out:
+	} else {
+		attr->xattri_dela_state =
+			xfs_attr_complete_op(attr, XFS_DAS_LEAF_REPLACE);
+	}
+
 	trace_xfs_attr_leaf_addname_return(attr->xattri_dela_state, args->dp);
+	return 0;
+
+out_brelse:
+	xfs_trans_brelse(args->trans, bp);
 	return error;
 }
 
@@ -546,7 +597,7 @@ xfs_attr_node_addname(
 		return error;
 
 	error = xfs_attr_node_try_addname(attr);
-	if (error == -ENOSPC) {
+	if (error == 1) {
 		error = xfs_attr3_leaf_to_node(args);
 		if (error)
 			return error;
@@ -1170,88 +1221,6 @@ xfs_attr_shortform_addname(
  * External routines when attribute list is one block
  *========================================================================*/
 
-/* Save the current remote block info and clear the current pointers. */
-static void
-xfs_attr_save_rmt_blk(
-	struct xfs_da_args	*args)
-{
-	args->blkno2 = args->blkno;
-	args->index2 = args->index;
-	args->rmtblkno2 = args->rmtblkno;
-	args->rmtblkcnt2 = args->rmtblkcnt;
-	args->rmtvaluelen2 = args->rmtvaluelen;
-	args->rmtblkno = 0;
-	args->rmtblkcnt = 0;
-	args->rmtvaluelen = 0;
-}
-
-/* Set stored info about a remote block */
-static void
-xfs_attr_restore_rmt_blk(
-	struct xfs_da_args	*args)
-{
-	args->blkno = args->blkno2;
-	args->index = args->index2;
-	args->rmtblkno = args->rmtblkno2;
-	args->rmtblkcnt = args->rmtblkcnt2;
-	args->rmtvaluelen = args->rmtvaluelen2;
-}
-
-/*
- * Tries to add an attribute to an inode in leaf form
- *
- * This function is meant to execute as part of a delayed operation and leaves
- * the transaction handling to the caller.  On success the attribute is added
- * and the inode and transaction are left dirty.  If there is not enough space,
- * the attr data is converted to node format and -ENOSPC is returned. Caller is
- * responsible for handling the dirty inode and transaction or adding the attr
- * in node format.
- */
-STATIC int
-xfs_attr_leaf_try_add(
-	struct xfs_da_args	*args)
-{
-	struct xfs_buf		*bp;
-	int			error;
-
-	error = xfs_attr3_leaf_read(args->trans, args->dp, args->owner, 0, &bp);
-	if (error)
-		return error;
-
-	/*
-	 * Look up the xattr name to set the insertion point for the new xattr.
-	 */
-	error = xfs_attr3_leaf_lookup_int(bp, args);
-	switch (error) {
-	case -ENOATTR:
-		if (args->op_flags & XFS_DA_OP_REPLACE)
-			goto out_brelse;
-		break;
-	case -EEXIST:
-		if (!(args->op_flags & XFS_DA_OP_REPLACE))
-			goto out_brelse;
-
-		trace_xfs_attr_leaf_replace(args);
-		/*
-		 * Save the existing remote attr state so that the current
-		 * values reflect the state of the new attribute we are about to
-		 * add, not the attribute we just found and will remove later.
-		 */
-		xfs_attr_save_rmt_blk(args);
-		break;
-	case 0:
-		break;
-	default:
-		goto out_brelse;
-	}
-
-	return xfs_attr3_leaf_add(bp, args);
-
-out_brelse:
-	xfs_trans_brelse(args->trans, bp);
-	return error;
-}
-
 /*
  * Return EEXIST if attr is found, or ENOATTR if not
  */
@@ -1417,9 +1386,12 @@ xfs_attr_node_addname_find_attr(
 /*
  * Add a name to a Btree-format attribute list.
  *
- * This will involve walking down the Btree, and may involve splitting
- * leaf nodes and even splitting intermediate nodes up to and including
- * the root node (a special case of an intermediate node).
+ * This will involve walking down the Btree, and may involve splitting leaf
+ * nodes and even splitting intermediate nodes up to and including the root
+ * node (a special case of an intermediate node).
+ *
+ * If the tree was still in single leaf format and needs to converted to
+ * real node format return 1 and let the caller handle that.
  */
 static int
 xfs_attr_node_try_addname(
@@ -1427,21 +1399,21 @@ xfs_attr_node_try_addname(
 {
 	struct xfs_da_state		*state = attr->xattri_da_state;
 	struct xfs_da_state_blk		*blk;
-	int				error;
+	int				error = 0;
 
 	trace_xfs_attr_node_addname(state->args);
 
 	blk = &state->path.blk[state->path.active-1];
 	ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
 
-	error = xfs_attr3_leaf_add(blk->bp, state->args);
-	if (error == -ENOSPC) {
+	if (!xfs_attr3_leaf_add(blk->bp, state->args)) {
 		if (state->path.active == 1) {
 			/*
 			 * Its really a single leaf node, but it had
 			 * out-of-line values so it looked like it *might*
 			 * have been a b-tree. Let the caller deal with this.
 			 */
+			error = 1;
 			goto out;
 		}
 

fs/xfs/libxfs/xfs_attr_leaf.c

@@ -47,7 +47,7 @@
  */
 STATIC int xfs_attr3_leaf_create(struct xfs_da_args *args,
 				 xfs_dablk_t which_block, struct xfs_buf **bpp);
-STATIC int xfs_attr3_leaf_add_work(struct xfs_buf *leaf_buffer,
+STATIC void xfs_attr3_leaf_add_work(struct xfs_buf *leaf_buffer,
 				   struct xfs_attr3_icleaf_hdr *ichdr,
 				   struct xfs_da_args *args, int freemap_index);
 STATIC void xfs_attr3_leaf_compact(struct xfs_da_args *args,
@@ -995,10 +995,8 @@ xfs_attr_shortform_to_leaf(
 		xfs_attr_sethash(&nargs);
 		error = xfs_attr3_leaf_lookup_int(bp, &nargs); /* set a->index */
 		ASSERT(error == -ENOATTR);
-		error = xfs_attr3_leaf_add(bp, &nargs);
-		ASSERT(error != -ENOSPC);
-		if (error)
-			goto out;
+		if (!xfs_attr3_leaf_add(bp, &nargs))
+			ASSERT(0);
 		sfe = xfs_attr_sf_nextentry(sfe);
 	}
 	error = 0;
@@ -1333,6 +1331,9 @@ xfs_attr3_leaf_create(
 
 /*
  * Split the leaf node, rebalance, then add the new entry.
+ *
+ * Returns 0 if the entry was added, 1 if a further split is needed or a
+ * negative error number otherwise.
  */
 int
 xfs_attr3_leaf_split(
@@ -1340,8 +1341,9 @@ xfs_attr3_leaf_split(
 	struct xfs_da_state_blk	*oldblk,
 	struct xfs_da_state_blk	*newblk)
 {
-	xfs_dablk_t blkno;
-	int error;
+	bool			added;
+	xfs_dablk_t		blkno;
+	int			error;
 
 	trace_xfs_attr_leaf_split(state->args);
 
@@ -1376,10 +1378,10 @@ xfs_attr3_leaf_split(
 	 */
 	if (state->inleaf) {
 		trace_xfs_attr_leaf_add_old(state->args);
-		error = xfs_attr3_leaf_add(oldblk->bp, state->args);
+		added = xfs_attr3_leaf_add(oldblk->bp, state->args);
 	} else {
 		trace_xfs_attr_leaf_add_new(state->args);
-		error = xfs_attr3_leaf_add(newblk->bp, state->args);
+		added = xfs_attr3_leaf_add(newblk->bp, state->args);
 	}
 
 	/*
@@ -1387,13 +1389,15 @@ xfs_attr3_leaf_split(
 	 */
 	oldblk->hashval = xfs_attr_leaf_lasthash(oldblk->bp, NULL);
 	newblk->hashval = xfs_attr_leaf_lasthash(newblk->bp, NULL);
-	return error;
+	if (!added)
+		return 1;
+	return 0;
 }
 
 /*
  * Add a name to the leaf attribute list structure.
  */
-int
+bool
 xfs_attr3_leaf_add(
 	struct xfs_buf		*bp,
 	struct xfs_da_args	*args)
@@ -1402,6 +1406,7 @@ xfs_attr3_leaf_add(
 	struct xfs_attr3_icleaf_hdr ichdr;
 	int			tablesize;
 	int			entsize;
+	bool			added = true;
 	int			sum;
 	int			tmp;
 	int			i;
@@ -1430,7 +1435,7 @@ xfs_attr3_leaf_add(
 		if (ichdr.freemap[i].base < ichdr.firstused)
 			tmp += sizeof(xfs_attr_leaf_entry_t);
 		if (ichdr.freemap[i].size >= tmp) {
-			tmp = xfs_attr3_leaf_add_work(bp, &ichdr, args, i);
+			xfs_attr3_leaf_add_work(bp, &ichdr, args, i);
 			goto out_log_hdr;
 		}
 		sum += ichdr.freemap[i].size;
@@ -1442,7 +1447,7 @@ xfs_attr3_leaf_add(
 	 * no good and we should just give up.
 	 */
 	if (!ichdr.holes && sum < entsize)
-		return -ENOSPC;
+		return false;
 
 	/*
 	 * Compact the entries to coalesce free space.
@@ -1455,24 +1460,24 @@ xfs_attr3_leaf_add(
 	 * free region, in freemap[0].  If it is not big enough, give up.
 	 */
 	if (ichdr.freemap[0].size < (entsize + sizeof(xfs_attr_leaf_entry_t))) {
-		tmp = -ENOSPC;
+		added = false;
 		goto out_log_hdr;
 	}
 
-	tmp = xfs_attr3_leaf_add_work(bp, &ichdr, args, 0);
+	xfs_attr3_leaf_add_work(bp, &ichdr, args, 0);
 
 out_log_hdr:
 	xfs_attr3_leaf_hdr_to_disk(args->geo, leaf, &ichdr);
 	xfs_trans_log_buf(args->trans, bp,
 		XFS_DA_LOGRANGE(leaf, &leaf->hdr,
 				xfs_attr3_leaf_hdr_size(leaf)));
-	return tmp;
+	return added;
 }
 
 /*
  * Add a name to a leaf attribute list structure.
  */
-STATIC int
+STATIC void
 xfs_attr3_leaf_add_work(
 	struct xfs_buf		*bp,
 	struct xfs_attr3_icleaf_hdr *ichdr,
@@ -1590,7 +1595,6 @@ xfs_attr3_leaf_add_work(
 		}
 	}
 	ichdr->usedbytes += xfs_attr_leaf_entsize(leaf, args->index);
-	return 0;
 }
 
 /*

fs/xfs/libxfs/xfs_attr_leaf.h

@@ -76,7 +76,7 @@ int	xfs_attr3_leaf_split(struct xfs_da_state *state,
 int	xfs_attr3_leaf_lookup_int(struct xfs_buf *leaf,
 					struct xfs_da_args *args);
 int	xfs_attr3_leaf_getvalue(struct xfs_buf *bp, struct xfs_da_args *args);
-int	xfs_attr3_leaf_add(struct xfs_buf *leaf_buffer,
+bool	xfs_attr3_leaf_add(struct xfs_buf *leaf_buffer,
 				 struct xfs_da_args *args);
 int	xfs_attr3_leaf_remove(struct xfs_buf *leaf_buffer,
 				    struct xfs_da_args *args);

fs/xfs/libxfs/xfs_bmap.c

@@ -3477,31 +3477,19 @@ xfs_bmap_process_allocated_extent(
 	xfs_bmap_alloc_account(ap);
 }
 
-#ifdef DEBUG
 static int
 xfs_bmap_exact_minlen_extent_alloc(
-	struct xfs_bmalloca	*ap)
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args)
 {
-	struct xfs_mount	*mp = ap->ip->i_mount;
-	struct xfs_alloc_arg	args = { .tp = ap->tp, .mp = mp };
-	xfs_fileoff_t		orig_offset;
-	xfs_extlen_t		orig_length;
-	int			error;
-
-	ASSERT(ap->length);
-
 	if (ap->minlen != 1) {
-		ap->blkno = NULLFSBLOCK;
-		ap->length = 0;
+		args->fsbno = NULLFSBLOCK;
 		return 0;
 	}
 
-	orig_offset = ap->offset;
-	orig_length = ap->length;
-
-	args.alloc_minlen_only = 1;
-
-	xfs_bmap_compute_alignments(ap, &args);
+	args->alloc_minlen_only = 1;
+	args->minlen = args->maxlen = ap->minlen;
+	args->total = ap->total;
 
 	/*
 	 * Unlike the longest extent available in an AG, we don't track
@@ -3511,39 +3499,16 @@ xfs_bmap_exact_minlen_extent_alloc(
 	 * we need not be concerned about a drop in performance in
 	 * "debug only" code paths.
 	 */
-	ap->blkno = XFS_AGB_TO_FSB(mp, 0, 0);
+	ap->blkno = XFS_AGB_TO_FSB(ap->ip->i_mount, 0, 0);
 
-	args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
-	args.minlen = args.maxlen = ap->minlen;
-	args.total = ap->total;
-
-	args.alignment = 1;
-	args.minalignslop = 0;
-
-	args.minleft = ap->minleft;
-	args.wasdel = ap->wasdel;
-	args.resv = XFS_AG_RESV_NONE;
-	args.datatype = ap->datatype;
-
-	error = xfs_alloc_vextent_first_ag(&args, ap->blkno);
-	if (error)
-		return error;
-
-	if (args.fsbno != NULLFSBLOCK) {
-		xfs_bmap_process_allocated_extent(ap, &args, orig_offset,
-			orig_length);
-	} else {
-		ap->blkno = NULLFSBLOCK;
-		ap->length = 0;
-	}
-
-	return 0;
+	/*
+	 * Call xfs_bmap_btalloc_low_space here as it first does a "normal" AG
+	 * iteration and then drops args->total to args->minlen, which might be
+	 * required to find an allocation for the transaction reservation when
+	 * the file system is very full.
+	 */
+	return xfs_bmap_btalloc_low_space(ap, args);
 }
-#else
-
-#define xfs_bmap_exact_minlen_extent_alloc(bma) (-EFSCORRUPTED)
-
-#endif
 
 /*
  * If we are not low on available data blocks and we are allocating at
@@ -3801,8 +3766,11 @@ xfs_bmap_btalloc(
 	/* Trim the allocation back to the maximum an AG can fit. */
 	args.maxlen = min(ap->length, mp->m_ag_max_usable);
 
-	if ((ap->datatype & XFS_ALLOC_USERDATA) &&
-	    xfs_inode_is_filestream(ap->ip))
+	if (unlikely(XFS_TEST_ERROR(false, mp,
+			XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT)))
+		error = xfs_bmap_exact_minlen_extent_alloc(ap, &args);
+	else if ((ap->datatype & XFS_ALLOC_USERDATA) &&
+			xfs_inode_is_filestream(ap->ip))
 		error = xfs_bmap_btalloc_filestreams(ap, &args, stripe_align);
 	else
 		error = xfs_bmap_btalloc_best_length(ap, &args, stripe_align);
@@ -4176,43 +4144,6 @@ xfs_bmapi_reserve_delalloc(
 	return error;
 }
 
-static int
-xfs_bmap_alloc_userdata(
-	struct xfs_bmalloca	*bma)
-{
-	struct xfs_mount	*mp = bma->ip->i_mount;
-	int			whichfork = xfs_bmapi_whichfork(bma->flags);
-	int			error;
-
-	/*
-	 * Set the data type being allocated. For the data fork, the first data
-	 * in the file is treated differently to all other allocations. For the
-	 * attribute fork, we only need to ensure the allocated range is not on
-	 * the busy list.
-	 */
-	bma->datatype = XFS_ALLOC_NOBUSY;
-	if (whichfork == XFS_DATA_FORK || whichfork == XFS_COW_FORK) {
-		bma->datatype |= XFS_ALLOC_USERDATA;
-		if (bma->offset == 0)
-			bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA;
-
-		if (mp->m_dalign && bma->length >= mp->m_dalign) {
-			error = xfs_bmap_isaeof(bma, whichfork);
-			if (error)
-				return error;
-		}
-
-		if (XFS_IS_REALTIME_INODE(bma->ip))
-			return xfs_bmap_rtalloc(bma);
-	}
-
-	if (unlikely(XFS_TEST_ERROR(false, mp,
-			XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT)))
-		return xfs_bmap_exact_minlen_extent_alloc(bma);
-
-	return xfs_bmap_btalloc(bma);
-}
-
 static int
 xfs_bmapi_allocate(
 	struct xfs_bmalloca	*bma)
@@ -4230,15 +4161,32 @@ xfs_bmapi_allocate(
 	else
 		bma->minlen = 1;
 
-	if (bma->flags & XFS_BMAPI_METADATA) {
-		if (unlikely(XFS_TEST_ERROR(false, mp,
-				XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT)))
-			error = xfs_bmap_exact_minlen_extent_alloc(bma);
-		else
-			error = xfs_bmap_btalloc(bma);
-	} else {
-		error = xfs_bmap_alloc_userdata(bma);
+	if (!(bma->flags & XFS_BMAPI_METADATA)) {
+		/*
+		 * For the data and COW fork, the first data in the file is
+		 * treated differently to all other allocations. For the
+		 * attribute fork, we only need to ensure the allocated range
+		 * is not on the busy list.
+		 */
+		bma->datatype = XFS_ALLOC_NOBUSY;
+		if (whichfork == XFS_DATA_FORK || whichfork == XFS_COW_FORK) {
+			bma->datatype |= XFS_ALLOC_USERDATA;
+			if (bma->offset == 0)
+				bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA;
+
+			if (mp->m_dalign && bma->length >= mp->m_dalign) {
+				error = xfs_bmap_isaeof(bma, whichfork);
+				if (error)
+					return error;
+			}
+		}
 	}
+
+	if ((bma->datatype & XFS_ALLOC_USERDATA) &&
+	    XFS_IS_REALTIME_INODE(bma->ip))
+		error = xfs_bmap_rtalloc(bma);
+	else
+		error = xfs_bmap_btalloc(bma);
 	if (error)
 		return error;
 	if (bma->blkno == NULLFSBLOCK)

fs/xfs/libxfs/xfs_da_btree.c

@@ -593,9 +593,8 @@ xfs_da3_split(
 		switch (oldblk->magic) {
 		case XFS_ATTR_LEAF_MAGIC:
 			error = xfs_attr3_leaf_split(state, oldblk, newblk);
-			if ((error != 0) && (error != -ENOSPC)) {
+			if (error < 0)
 				return error;	/* GROT: attr is inconsistent */
-			}
 			if (!error) {
 				addblk = newblk;
 				break;
@@ -617,6 +616,8 @@ xfs_da3_split(
 				error = xfs_attr3_leaf_split(state, newblk,
 							    &state->extrablk);
 			}
+			if (error == 1)
+				return -ENOSPC;
 			if (error)
 				return error;	/* GROT: attr inconsistent */
 			addblk = newblk;

fs/xfs/scrub/ialloc_repair.c

@@ -657,7 +657,7 @@ xrep_ibt_build_new_trees(
 	 * Start by setting up the inobt staging cursor.
 	 */
 	fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
-			XFS_IBT_BLOCK(sc->mp)),
+			XFS_IBT_BLOCK(sc->mp));
 	xrep_newbt_init_ag(&ri->new_inobt, sc, &XFS_RMAP_OINFO_INOBT, fsbno,
 			XFS_AG_RESV_NONE);
 	ri->new_inobt.bload.claim_block = xrep_ibt_claim_block;
@@ -678,7 +678,7 @@ xrep_ibt_build_new_trees(
 			resv = XFS_AG_RESV_NONE;
 
 		fsbno = XFS_AGB_TO_FSB(sc->mp, sc->sa.pag->pag_agno,
-				XFS_FIBT_BLOCK(sc->mp)),
+				XFS_FIBT_BLOCK(sc->mp));
 		xrep_newbt_init_ag(&ri->new_finobt, sc, &XFS_RMAP_OINFO_INOBT,
 				fsbno, resv);
 		ri->new_finobt.bload.claim_block = xrep_fibt_claim_block;

fs/xfs/xfs_icache.c

@@ -1280,14 +1280,17 @@ xfs_inode_clear_eofblocks_tag(
 }
 
 /*
- * Set ourselves up to free CoW blocks from this file.  If it's already clean
- * then we can bail out quickly, but otherwise we must back off if the file
- * is undergoing some kind of write.
+ * Prepare to free COW fork blocks from an inode.
  */
 static bool
 xfs_prep_free_cowblocks(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	struct xfs_icwalk	*icw)
 {
+	bool			sync;
+
+	sync = icw && (icw->icw_flags & XFS_ICWALK_FLAG_SYNC);
+
 	/*
 	 * Just clear the tag if we have an empty cow fork or none at all. It's
 	 * possible the inode was fully unshared since it was originally tagged.
@@ -1299,16 +1302,22 @@ xfs_prep_free_cowblocks(
 	}
 
 	/*
-	 * If the mapping is dirty or under writeback we cannot touch the
-	 * CoW fork.  Leave it alone if we're in the midst of a directio.
+	 * A cowblocks trim of an inode can have a significant effect on
+	 * fragmentation even when a reasonable COW extent size hint is set.
+	 * Therefore, we prefer to not process cowblocks unless they are clean
+	 * and idle. We can never process a cowblocks inode that is dirty or has
+	 * in-flight I/O under any circumstances, because outstanding writeback
+	 * or dio expects targeted COW fork blocks exist through write
+	 * completion where they can be remapped into the data fork.
+	 *
+	 * Therefore, the heuristic used here is to never process inodes
+	 * currently opened for write from background (i.e. non-sync) scans. For
+	 * sync scans, use the pagecache/dio state of the inode to ensure we
+	 * never free COW fork blocks out from under pending I/O.
 	 */
-	if ((VFS_I(ip)->i_state & I_DIRTY_PAGES) ||
-	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) ||
-	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_WRITEBACK) ||
-	    atomic_read(&VFS_I(ip)->i_dio_count))
+	if (!sync && inode_is_open_for_write(VFS_I(ip)))
 		return false;
-
-	return true;
+	return xfs_can_free_cowblocks(ip);
 }
 
 /*
@@ -1337,7 +1346,7 @@ xfs_inode_free_cowblocks(
 	if (!xfs_iflags_test(ip, XFS_ICOWBLOCKS))
 		return 0;
 
-	if (!xfs_prep_free_cowblocks(ip))
+	if (!xfs_prep_free_cowblocks(ip, icw))
 		return 0;
 
 	if (!xfs_icwalk_match(ip, icw))
@@ -1366,7 +1375,7 @@ xfs_inode_free_cowblocks(
 	 * Check again, nobody else should be able to dirty blocks or change
 	 * the reflink iflag now that we have the first two locks held.
 	 */
-	if (xfs_prep_free_cowblocks(ip))
+	if (xfs_prep_free_cowblocks(ip, icw))
 		ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 	return ret;
 }

fs/xfs/xfs_log.h

@@ -158,6 +158,4 @@ bool	xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t);
 
 bool	  xlog_force_shutdown(struct xlog *log, uint32_t shutdown_flags);
 
-int xfs_attr_use_log_assist(struct xfs_mount *mp);
-
 #endif	/* __XFS_LOG_H__ */

fs/xfs/xfs_log_cil.c

@@ -156,7 +156,6 @@ xlog_cil_insert_pcp_aggregate(
 	struct xfs_cil		*cil,
 	struct xfs_cil_ctx	*ctx)
 {
-	struct xlog_cil_pcp	*cilpcp;
 	int			cpu;
 	int			count = 0;
 
@@ -171,13 +170,11 @@ xlog_cil_insert_pcp_aggregate(
 	 * structures that could have a nonzero space_used.
 	 */
 	for_each_cpu(cpu, &ctx->cil_pcpmask) {
-		int	old, prev;
+		struct xlog_cil_pcp	*cilpcp = per_cpu_ptr(cil->xc_pcp, cpu);
+		int			old = READ_ONCE(cilpcp->space_used);
 
-		cilpcp = per_cpu_ptr(cil->xc_pcp, cpu);
-		do {
-			old = cilpcp->space_used;
-			prev = cmpxchg(&cilpcp->space_used, old, 0);
-		} while (old != prev);
+		while (!try_cmpxchg(&cilpcp->space_used, &old, 0))
+			;
 		count += old;
 	}
 	atomic_add(count, &ctx->space_used);

fs/xfs/xfs_log_recover.c

@@ -1849,7 +1849,7 @@ xlog_find_item_ops(
  *	   from the transaction. However, we can't do that until after we've
  *	   replayed all the other items because they may be dependent on the
  *	   cancelled buffer and replaying the cancelled buffer can remove it
- *	   form the cancelled buffer table. Hence they have tobe done last.
+ *	   form the cancelled buffer table. Hence they have to be done last.
  *
  *	3. Inode allocation buffers must be replayed before inode items that
  *	   read the buffer and replay changes into it. For filesystems using the

fs/xfs/xfs_reflink.c

@@ -1595,6 +1595,9 @@ xfs_reflink_clear_inode_flag(
 
 	ASSERT(xfs_is_reflink_inode(ip));
 
+	if (!xfs_can_free_cowblocks(ip))
+		return 0;
+
 	error = xfs_reflink_inode_has_shared_extents(*tpp, ip, &needs_flag);
 	if (error || needs_flag)
 		return error;

fs/xfs/xfs_reflink.h

@@ -6,6 +6,25 @@
 #ifndef __XFS_REFLINK_H
 #define __XFS_REFLINK_H 1
 
+/*
+ * Check whether it is safe to free COW fork blocks from an inode. It is unsafe
+ * to do so when an inode has dirty cache or I/O in-flight, even if no shared
+ * extents exist in the data fork, because outstanding I/O may target blocks
+ * that were speculatively allocated to the COW fork.
+ */
+static inline bool
+xfs_can_free_cowblocks(struct xfs_inode *ip)
+{
+	struct inode *inode = VFS_I(ip);
+
+	if ((inode->i_state & I_DIRTY_PAGES) ||
+	    mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY) ||
+	    mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK) ||
+	    atomic_read(&inode->i_dio_count))
+		return false;
+	return true;
+}
+
 extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *irec, bool *shared);
 int xfs_bmap_trim_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,